Machine learning (ML) finds extensive utility across diverse engineering domains, serving a myriad of purposes. Within the realm of power systems, traditional fault detection relies on relays and measurement equipment to pinpoint anomalies. These anomalies are subsequently categorized based on their characteristics. ML tools offer the prospect of crafting algorithms capable of forecasting these faults. This study entails the emulation of a power distribution system within software, employing machine learning algorithms to predict faults. The dependable and efficient operation of power systems stands as a pivotal factor in guaranteeing a constant power supply, thereby satisfying the requirements of contemporary society. Through the application of these methods, our aim is to create a more effective and precise fault detection algorithm tailored for three-phase power systems. This article delves into the intricacies linked with forecasting faults in power systems, provides an overview of pertinent ML methodologies, and delivers a case study that illustrates the efficacy of ML-driven intelligent fault prediction within real-world power system scenarios.

Maine Learning, Fault, Power system, Algorithms, Fault detection, Prediction

[1] A. Firos, N. Prakash, R. Gorthi, M. Soni, S. Kumar and V. Balaraju, ”Fault Detection in Power Transmission Lines Using AI Model,” 2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India, pp.1-6, 2023.
[2] Manojna, Sridhar H. S, Nikhil Nikhil, Anand Kumar, and Pratyay Amrit. Fault detection and classification in power system using machine learning. In 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC), pp.1801– 1806, 2021.
[3] Nouha Bouchiba and Azeddine Kaddouri. Application of machine learning algorithms for power systems fault detection. In 2021 9th International Conference on Systems and Control (ICSC), pp.127–132, 2021.
[4] Nikola Markovic, Thomas Stoetzel, Volker Staudt, and Dorothea Kolossa. Hybrid fault detection in power systems. In 2019 IEEE International Electric Machines and Drives Conference (IEMDC), pp.911–915, 2019.
[5] Halil Alper Tokel, Rana Al Halaseh, Gholamreza Alirezaei, and Rudolf Mathar. A new approach for machine learning-based fault detection and classification in power systems. In 2018 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference (ISGT), pp.1–5, 2018.
[6] Rachna Vaish and U.D. Dwivedi. Comparative study of machine learning models for power system fault identification and localization. In 2021 4th International Conference on Recent Trends in Computer Science and Technology (ICRTCST), pp.110– 115, 2022.
[7] Akshay Ajagekar and Fengqi You. Quantum computing based hybrid deep learning for fault diagnosis in electrical power systems. Applied Energy, 303:117628, 2021
[8] Helon Vicente Hultmann Ayala, Didace Habineza, Micky Rakotondrabe, and Leandro dos Santos Coelho. Nonlinear black-box system identification through coevolutionary algorithms and radial basis function artificial neural networks. Applied Soft Computing, 87:105990, 2020
[9] Bilal, Millie Pant, Hira Zaheer, Laura Garcia-Hernandez, and Ajith Abraham. Differential evolution: A review of more than two decades of research. Engineering Applications of Artificial Intelligence, 90:103479, 2020
[10] Shahriar Rahman Fahim, Yeahia Sarker, Subrata K. Sarker, Md. Rafiqul Islam Sheikh, and Sajal K. Das. Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification. Electric Power Systems Research, 187:106437, 2020.
[11] Hassan Fathabadi. Novel filter based ann approach for shortcircuit faults detection, classification and location in power transmission lines. International Journal of Electrical Power and Energy Systems, 74: pp.374–383, 2016
[12] Hassan Fathabadi. Novel filter based ann approach for shortcircuit faults detection, classification and location in power transmission lines. International Journal of Electrical Power and Energy Systems, 74: pp.374–383, 2016
[13] O.A. Gashteroodkhani, M. Majidi, M. Etezadi-Amoli, A.F. Nematollahi, and B. Vahidi. A hybrid svm-tt transform-based method for fault location in hybrid transmission lines with underground cables. Electric Power Systems Research, 170: pp.205–214, 2019.
[14] Alireza Ghaedi, Mohammad Esmail Hamedani Golshan, and Majid Sanaye-Pasand. Transmission line fault location based on threephase state estimation framework considering measurement chain error model. Electric Power Systems Research, 178:106048, 2020.
[15] Mevludin Glavic. (deep) reinforcement learning for electric power system control and related problems: A short review and perspectives. Annual Reviews in Control, 48: pp.22–35, 2019.
[16] Sandeep Kumar Verma, Turendar Sahu, Manjit Jaiswal, (2019). A Deep Analysis and Efficient Implementation of Supervised Machine Learning Algorithms for Enhancing The Classification Ability of System. International Journal of Computer Sciences and Engineering, Vol.7, Issue.3, pp.1094-1101, 2019.
[17] Harsh H. Patel, Purvi Prajapati, (2018). Study and Analysis of Decision Tree Based Classification Algorithms. International Journal of Computer Sciences and Engineering, Vol.6, Issue.10, pp.74-78, 2018.